Adaptive sFFLHD sampling concept

Collin Erickson
7/13/2016

What I've worked on

Implemented sFFLHD
Adaptive sampling concept
- Sample, then focus on subregion or return up level
Combined these two to get adaptive sFFLHD sampling

sFFLHD

s <- sFFLHD.seq(D = 3, L = 5)
s$get.batch()

           [,1]       [,2]       [,3]
[1,] 0.80704681 0.76735849 0.02498429
[2,] 0.07001103 0.54852614 0.76341669
[3,] 0.61340117 0.82163175 0.58389773
[4,] 0.37208543 0.32099826 0.25862690
[5,] 0.59966032 0.05542548 0.85744879

sFFLHD plot test

s <- sFFLHD.seq(D = 2, L = 5)
plot(NULL, xlim=0:1, ylim=0:1)
abline(h=(0:5)/5, v=(0:5)/5)
for(i in 1:5) points(s$get.batch(), col=i, pch=19)

plot of chunk unnamed-chunk-3

s <- sFFLHD.seq(D = 2, L = 3)
l <- 9
plot(NULL, xlim=0:1, ylim=0:1)
abline(h=(0:l)/l, v=(0:l)/l)
for(i in 1:27) points(s$get.batch(), col=i, pch=19)

plot of chunk unnamed-chunk-4

[1] "Going one deeper"

Example: Gaussian

Actual function: Gaussian

contourfilled.func(gaussian1)

plot of chunk unnamed-chunk-6

plot of chunk unnamed-chunk-8

plot of chunk unnamed-chunk-10

plot of chunk unnamed-chunk-11

plot of chunk unnamed-chunk-12

plot of chunk unnamed-chunk-13

plot of chunk unnamed-chunk-14

plot of chunk unnamed-chunk-15

[1] "Going one deeper"

plot of chunk unnamed-chunk-16

Example: Sinumoid

Actual function: Sinusoid with a plateau

contourfilled.func(sinumoid)

plot of chunk unnamed-chunk-19

plot of chunk unnamed-chunk-20

plot of chunk unnamed-chunk-21

plot of chunk unnamed-chunk-22

plot of chunk unnamed-chunk-24

[1] "Going one deeper"

plot of chunk unnamed-chunk-25

plot of chunk unnamed-chunk-26

plot of chunk unnamed-chunk-27

plot of chunk unnamed-chunk-28